Triple

T19405102
Position Surface form Disambiguated ID Type / Status
Subject Museo de Arte Contemporáneo de Santiago E485431 entity
Predicate hasAbbreviation P43 FINISHED
Object MAC
MAC is a contemporary art museum in Santiago, Chile, known for exhibiting modern and contemporary artworks from Chilean and international artists.
E1374227 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: MAC | Statement: [Museo de Arte Contemporáneo de Santiago, hasAbbreviation, MAC]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: MAC
Context triple: [Museo de Arte Contemporáneo de Santiago, hasAbbreviation, MAC]
  • A. MAC
    MAC is the acronym for the Military Armistice Commission, the body responsible for supervising the implementation of the Korean Armistice Agreement.
  • B. MAC
    The MAC is a regional museum in Spokane, Washington, featuring art, history, and cultural exhibits focused on the Inland Northwest.
  • C. MAC
    MAC is the common abbreviation for the Macon Bacon, a collegiate summer baseball team based in Macon, Georgia.
  • D. MAC
    MAC is the ICAO airline designator assigned to Air Arabia Maroc, a Moroccan low-cost carrier.
  • E. MAC
    MAC is the IATA airport code for Macon Downtown Airport, a public airport serving the city of Macon, Georgia, in the United States.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: MAC
Triple: [Museo de Arte Contemporáneo de Santiago, hasAbbreviation, MAC]
Generated description
MAC is a contemporary art museum in Santiago, Chile, known for exhibiting modern and contemporary artworks from Chilean and international artists.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: MAC
Target entity description: MAC is a contemporary art museum in Santiago, Chile, known for exhibiting modern and contemporary artworks from Chilean and international artists.
  • A. MAC
    The MAC is a regional museum in Spokane, Washington, featuring art, history, and cultural exhibits focused on the Inland Northwest.
  • B. MAC
    MAC is the commonly used abbreviation for the Mid-Atlantic Center for the Arts & Humanities, a cultural organization dedicated to preserving and promoting the historic and artistic heritage of the Mid-Atlantic region.
  • C. MAC
    MAC is the commonly used abbreviation for the United Kingdom’s Migration Advisory Committee, an independent body that advises the government on immigration policy.
  • D. MAC
    MAC is the stock ticker symbol for The Macerich Company, a real estate investment trust specializing in shopping centers and retail properties in the United States.
  • E. MAC
    MAC is the IATA airport code for Macon Downtown Airport, a public airport serving the city of Macon, Georgia, in the United States.
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d8e8d5162481909db12435d9535c1a completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e6257a361c8190bf019fc350faa225 completed April 20, 2026, 1:09 p.m.
NED1 Entity disambiguation (via context triple) batch_6a072b95775481909a2d2c84ed8dac87 completed May 15, 2026, 2:20 p.m.
NEDg Description generation batch_6a072ed99d608190ab6515517cac95dc completed May 15, 2026, 2:34 p.m.
NED2 Entity disambiguation (via description) batch_6a072f5364648190954997b4da8248ef completed May 15, 2026, 2:36 p.m.
Created at: April 10, 2026, 1:36 p.m.